Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 669 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.5363. Min Act: -0.0002

Data Index: 1202404 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.5378. Min Act: -0.0001

Data Index: 1070509 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.5168. Min Act: -0.0001

Data Index: 1292866 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.5400. Min Act: -0.0002

Data Index: 1319848 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4578. Min Act: -0.0001

Data Index: 629880 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4563. Min Act: -0.0002

Data Index: 440558 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4865. Min Act: -0.0002

Data Index: 881741 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4723. Min Act: -0.0001

Data Index: 967158 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4542. Min Act: -0.0001

Data Index: 443791 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4814. Min Act: -0.0002

Data Index: 107296 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4451. Min Act: -0.0001

Data Index: 717668 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4297. Min Act: -0.0002

Data Index: 59378 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4571. Min Act: -0.0002

Data Index: 616944 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4261. Min Act: -0.0001

Data Index: 997230 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4040. Min Act: -0.0001

Data Index: 683791 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.3956. Min Act: -0.0001

Data Index: 392127 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4395. Min Act: -0.0001

Data Index: 161739 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4220. Min Act: -0.0001

Data Index: 998151 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4080. Min Act: -0.0001

Data Index: 969659 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.5400. Min Range: -0.5400

Max Act: 0.4385. Min Act: -0.0001

Data Index: 1286488 (C4 (Web Text))

Max Activating Token Index: 612